Training in progress, step 28, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d76418ff259d6b95ca3894a200164cb00ea783d60345b1fb1ae03590905f50
+oid sha256:3e9420f6f3fc29633a07c26c966bcb335bdc2f001c1272653d3ea778f90fe75f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94cb88358cbbf1e833e89a46774f1ccb301919b91d8d3bfff61c1c6334acd3b2
+oid sha256:3af919c555bec5b3888603008190cf11cf4bd7bea96f8db9233e3b5826dcd798
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c586bb87745295f65ce6d264680c04ef88ff6a0fdea5508bedcac1ab4611305
+oid sha256:43e032ef089020d5839ac578e9f697942b93e6f5e70ffa2f2e4ef22911f2f3bc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326fcf6627e93c7edf8930ecfe6cfc83b1de63b4028af99d8b84db2cd3f2b462
+oid sha256:0150c85cacd33a934780e6948dff1a6d8ed9a4be406087fb780c11d9e9c7811c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1689592efc1c2b6904f65ac9d1aaf0e6376585f6aaac6744fef8f54a5101a6a9
+oid sha256:5918b22653fdb96197b377b737ccda1244b18ac02e12732ec0b9ce22d350d8fa
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a118e681fa814e101b0fd54b5f7d177ef6c83e0e721bb9177ce578ce9b71a7
+oid sha256:b5d68508636586630def15adada56bacf5564430dadc7cdc60a1b731c838c499
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.73972602739726,
+  "epoch": 3.0684931506849313,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,27 @@
       "eval_samples_per_second": 15.47,
       "eval_steps_per_second": 4.022,
       "step": 25
+    },
+    {
+      "epoch": 2.8493150684931505,
+      "grad_norm": NaN,
+      "learning_rate": 1.130761821582766e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.958904109589041,
+      "grad_norm": NaN,
+      "learning_rate": 1.0328100665587574e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 3.0684931506849313,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -221,12 +242,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 3.342126825697444e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null